Distributed garbage collection

Abstract

There are two basic approachs to the problem of storage reclamation, process- and processor-based, named for the view point used to recognize when a particular piece of storage can be reclaimed. Examples of the processor approach include mark/sweep and copying algorithms and their variants, while reference counting schemes use a process view of the collection. It is argued that the process approach is better suited for distributed computation where links between dynamically allocated objects may cross processor boundaries. In addition, the process approach allows the heap to be more conveniently shared with other processes in those cases when different processes might not have their own virtual address spaces. A new algorithm using the process approach is given. Its space requirement per object is better than that for reference counting. In addition, a restricted form of pointer replacement is supported which allows circular structures so constructed to be properly collected.